Notice
This is not the latest version of this item. The latest version can be found at:https://dspace.mit.edu/handle/1721.1/137356.2
PRNet: Self-supervised learning for partial-to-partial registration
dc.date.accessioned | 2021-11-04T16:18:24Z | |
dc.date.available | 2021-11-04T16:18:24Z | |
dc.date.issued | 2019-12 | |
dc.date.submitted | 2019-12 | |
dc.identifier.uri | https://hdl.handle.net/1721.1/137356 | |
dc.description.abstract | © 2019 Neural information processing systems foundation. All rights reserved. We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning-based methods for registration, we use deep networks to tackle non-convexity of the alignment and partial correspondence problems. While previous learning-based methods assume the entire shape is visible, PRNet is suitable for partial-to-partial registration, outperforming PointNetLK, DCP, and non-learning methods on synthetic data. PRNet is self-supervised, jointly learning an appropriate geometric representation, a keypoint detector that finds points in common between partial views, and keypoint-to-keypoint correspondences. We show PRNet predicts keypoints and correspondences consistently across views and objects. Furthermore, the learned representation is transferable to classification. | en_US |
dc.language.iso | en | |
dc.rights | Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. | en_US |
dc.source | Neural Information Processing Systems (NIPS) | en_US |
dc.title | PRNet: Self-supervised learning for partial-to-partial registration | en_US |
dc.type | Article | en_US |
dc.identifier.citation | 2019. "PRNet: Self-supervised learning for partial-to-partial registration." Advances in Neural Information Processing Systems, 32. | |
dc.relation.journal | Advances in Neural Information Processing Systems | en_US |
dc.eprint.version | Final published version | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
eprint.status | http://purl.org/eprint/status/NonPeerReviewed | en_US |
dc.date.updated | 2021-03-26T14:01:18Z | |
dspace.orderedauthors | Wang, Y; Solomon, J | en_US |
dspace.date.submission | 2021-03-26T14:01:20Z | |
mit.journal.volume | 32 | en_US |
mit.license | PUBLISHER_POLICY | |
mit.metadata.status | Authority Work and Publication Information Needed | en_US |